Related Experiment Videos
Computer-aided detection in the United Kingdom National Breast Screening Programme: prospective study
Lisanne A L Khoo1, Paul Taylor, Rosalind M Given-Wilson
1Radiology Department, St George's Hospital, Blackshaw Rd, London SW17 0QT, England.
Radiology
|October 26, 2005
Summary
Computer-aided detection (CAD) slightly improves single-reader sensitivity in breast cancer screening but double reading offers a more substantial increase in cancer detection rates.
Area of Science:
- Radiology
- Medical Imaging
- Oncology
Background:
- Breast cancer screening programs aim to detect malignancies early.
- Computer-aided detection (CAD) systems are tools designed to assist radiologists.
Purpose of the Study:
- To prospectively evaluate the impact of CAD on recall and cancer detection rates.
- To compare single reading with and without CAD versus double reading.
Main Methods:
- Prospective analysis of mammograms from 6111 women in the UK National Health Service Breast Screening Programme.
- Independent double reading of mammograms, with and without CAD assistance.
- Calculation of sensitivity, cancer detection rate, and recall rate.
Main Results:
- CAD prompted 84% of detected cancers, improving single-reader sensitivity from 90.2% to 91.5%.
- Double reading without CAD achieved 98.4% sensitivity.
- CAD increased the recall to assessment rate by 5.8% and reading time by 20 seconds.
Conclusions:
- CAD offers a modest improvement in single-reader sensitivity for breast cancer detection.
- Double reading significantly enhances sensitivity compared to single reading, with or without CAD.